Triple
T7253257
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Pole Telescope |
E157654
|
entity |
| Predicate | surfaceAccuracy |
P56581
|
FINISHED |
| Object | tens of microns |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: tens of microns | Statement: [South Pole Telescope, surfaceAccuracy, tens of microns]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: surfaceAccuracy Context triple: [South Pole Telescope, surfaceAccuracy, tens of microns]
-
A.
surfaceQuality
Indicates the condition or characteristics of an entity’s outer surface, such as its smoothness, roughness, or finish.
-
B.
hasSurfaceAccuracy
chosen
Indicates that one entity possesses a specified degree or measure of accuracy related to its surface characteristics or representation.
-
C.
surfaceType
Indicates the kind or classification of surface associated with an entity or interaction.
-
D.
surfaceFeatureOf
Indicates that one entity is a surface-level characteristic, pattern, or feature belonging to or present on another entity.
-
E.
surfaceDescription
Indicates that one entity provides a textual or qualitative description of the surface characteristics or appearance of another entity.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69c6882d81d4819085f7ff862951ee4f |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea9d41908190bb76c6a5b9d5b1a2 |
completed | March 27, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69c6e7666ffc81908bf643d8257e6337 |
completed | March 27, 2026, 8:24 p.m. |
Created at: March 27, 2026, 2:56 p.m.